Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron is most sensitive to punctuation marks (especially commas) and list‐style separators.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     menstr
    -0.06
    ículos
    -0.06
    όν
    -0.06
    ";↵↵↵
    -0.06
    ulle
    -0.06
    ิโ
    -0.06
    اوية
    -0.05
    />";↵
    -0.05
    atrice
    -0.05
    .infinity
    -0.05
    POSITIVE LOGITS
     معمولا
    0.07
    verbs
    0.06
     converge
    0.06
     Rusya
    0.06
     incarcerated
    0.06
    lassen
    0.06
     Assume
    0.06
    usc
    0.06
     bakım
    0.06
     encount
    0.06
    Act Density 0.035%

    No Known Activations